Nearest-Neighbor and Logistic Regression Analyses of Clinical and Heart Rate Characteristics in the Early Diagnosis of Neonatal Sepsis
Authors:
- 18 June 2009
- journal article
- other
- Published by SAGE Publications in Medical Decision Making
- Vol. 30 (2) , 258-266
Abstract
Objectives. To test the hypothesis that nearest-neighbor analysis adds to logistic regression in the early diagnosis of late-onset neonatal sepsis. Design. The authors tested methods to make the early diagnosis of neonatal sepsis using continuous physiological monitoring of heart rate characteristics and intermittent measurements of laboratory values. First, the hypothesis that nearest-neighbor analysis makes reasonable predictions about neonatal sepsis with performance comparable to an existing logistic regression model was tested. The most parsimonious model was systematically developed by excluding the least efficacious clinical data. Second, the authors tested the hypothesis that a combined nearest-neighbor and logistic regression model gives an outcome prediction that is more plausible than either model alone. Training and test data sets of heart rate characteristics and laboratory test results over a 4-y period were used to create and test predictive models. Measurements. Nearest-neighbor, regression, and combination models were evaluated for discrimination using receiver-operating characteristic areas and for fit using the Wald statistic. Results. Both nearest-neighbor and regression models using heart rate characteristics and available laboratory test results were significantly associated with imminent sepsis, and each kind of model added independent information to the other. The best predictive strategy employed both kinds of models. Conclusion. The authors propose nearest-neighbor analysis in addition to regression in the early diagnosis of subacute, potentially catastrophic illnesses such as neonatal sepsis, and they recommend it as an approach to the general problem of predicting a clinical event from a multivariable data set.Keywords
This publication has 27 references indexed in Scilit:
- Heart Rate Characteristics Monitoring for Neonatal SepsisIEEE Transactions on Biomedical Engineering, 2005
- Heart Rate Characteristics: Novel Physiomarkers to Predict Neonatal Infection and DeathPediatrics, 2005
- Definitions of bloodstream infection in the newbornPediatric Critical Care Medicine, 2005
- Pediatric sepsis definitions: Past, present, and futurePediatric Critical Care Medicine, 2005
- What have we learned from observational studies on neonatal sepsis?Pediatric Critical Care Medicine, 2005
- Abnormal Heart Rate Characteristics Are Associated with Neonatal MortalityPediatric Research, 2004
- Abnormal Heart Rate Characteristics Preceding Neonatal Sepsis and Sepsis-Like IllnessPediatric Research, 2003
- Incidence, presenting features, risk factors and significance of late onset septicemia in very low birth weight infantsThe Pediatric Infectious Disease Journal, 1998
- A patient-specific algorithm for the detection of seizure onset in long-term EEG monitoring: possible use as a warning deviceIEEE Transactions on Biomedical Engineering, 1997
- CDC definitions for nosocomial infections, 1988American Journal of Infection Control, 1988